SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
cs.AI
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
- Reinforcement Learning for Long-Horizon Interactive LLM Agents
- Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Trajectory-Refined Distillation
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Constraint and Union for Partially-Supervised Temporal Sentence Grounding
- Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
- Multi-Turn On-Policy Distillation with Prefix Replay
- Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
- Understanding R1-Zero-Like Training: A Critical Perspective
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems